Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    缸
    -0.07
     Ether
    -0.07
    -To
    -0.07
     acrylic
    -0.07
    堾
    -0.07
     repay
    -0.07
    oyer
    -0.06
     engraved
    -0.06
     recognizer
    -0.06
    僰
    -0.06
    POSITIVE LOGITS
    _trees
    0.07
    𝕝
    0.07
     Glide
    0.07
     sle
    0.07
    oud
    0.06
    ❖
    0.06
    .cloud
    0.06
    もなく
    0.06
     flows
    0.06
    /views
    0.06
    Act Density 0.171%

    No Known Activations